Time filter

Source Type

Norinder U.,Swedish Toxicology science Research Center | Norinder U.,University of Stockholm | Rybacka A.,Umea University | Andersson P.L.,Umea University
SAR and QSAR in Environmental Research

A fundamental element when deriving a robust and predictive in silico model is not only the statistical quality of the model in question but, equally important, the estimate of its predictive boundaries. This work presents a new method, conformal prediction, for applicability domain estimation in the field of endocrine disruptors. The method is applied to binders and non-binders related to the oestrogen and androgen receptors. Ensembles of decision trees are used as statistical method and three different sets (dragon, rdkit and signature fingerprints) are investigated as chemical descriptors. The conformal prediction method results in valid models where there is an excellent balance in quality between the internally validated training set and the corresponding external test set, both in terms of validity and with respect to sensitivity and specificity. With this method the level of confidence can be readily altered by the user and the consequences thereof immediately inspected. Furthermore, the predictive boundaries for the derived models are rigorously defined by using the conformal prediction framework, thus no ambiguity exists as to the level of similarity needed for new compounds to be in or out of the predictive boundaries of the derived models where reliable predictions can be expected. © 2016 Informa UK Limited, trading as Taylor & Francis Group Source

Grimm F.A.,University of Iowa | Hu D.,University of Iowa | Kania-Korwel I.,University of Iowa | Lehmler H.-J.,University of Iowa | And 5 more authors.
Critical Reviews in Toxicology

The metabolism of polychlorinated biphenyls (PCBs) is complex and has an impact on toxicity, and thereby on the assessment of PCB risks. A large number of reactive and stable metabolites are formed in the processes of biotransformation in biota in general, and in humans in particular. The aim of this document is to provide an overview of PCB metabolism, and to identify the metabolites of concern and their occurrence. Emphasis is given to mammalian metabolism of PCBs and their hydroxyl, methylsulfonyl, and sulfated metabolites, especially those that persist in human blood. Potential intracellular targets and health risks are also discussed. © 2015 Informa Healthcare USA, Inc. Source

Gassen N.C.,Max Planck Institute of Psychiatry | Fries G.R.,Max Planck Institute of Psychiatry | Fries G.R.,University of Texas Health Science Center at Houston | Zannas A.S.,Max Planck Institute of Psychiatry | And 21 more authors.
Science Signaling

Epigenetic processes, such as DNA methylation, and molecular chaperones, including FK506-binding protein 51 (FKBP51), are independently implicated in stress-related mental disorders and antidepressant drug action. FKBP51 associates with cyclin-dependent kinase 5 (CDK5), which is one of several kinases that phosphorylates and activates DNA methyltransferase 1 (DNMT1). We searched for a functional link between FKBP51 (encoded by FKBP5) and DNMT1 in cells from mice and humans, including those from depressed patients, and found that FKBP51 competed with its close homolog FKBP52 for associationwith CDK5. In human embryonic kidney (HEK) 293 cells, expression of FKBP51 displaced FKBP52 from CDK5, decreased the interaction of CDK5 with DNMT1, reduced the phosphorylation and enzymatic activity of DNMT1, and diminished global DNA methylation. In mouse embryonic fibroblasts and primary mouse astrocytes, FKBP51 mediated several effects of paroxetine, namely, decreased the protein-protein interactions of DNMT1 with CDK5 and FKBP52, reduced phosphorylation of DNMT1, and decreased themethylation and increased the expression of the gene encoding brain-derived neurotrophic factor (Bdnf ). In human peripheral blood cells, FKBP5 expression inversely correlated with both global and BDNF methylation. Peripheral blood cells isolated from depressed patients that were thentreatedex vivowithparoxetine revealedthat the abundance of BDNF positively correlated and phosphorylated DNMT1 inversely correlated with that of FKBP51 in cells and with clinical treatment success in patients, supporting the relevance of this FKBP51- directed pathway that prevents epigenetic suppression of gene expression. Source

Capuccini M.,Uppsala University | Carlsson L.,Astrazeneca | Norinder U.,Swedish Toxicology science Research Center | Spjuth O.,Uppsala University
Proceedings - 2015 2nd IEEE/ACM International Symposium on Big Data Computing, BDC 2015

Increasing size of datasets is challenging for machine learning, and Big Data frameworks, such as Apache Spark, have shown promise for facilitating model building on distributed resources. Conformal prediction is a mathematical framework that allows to assign valid confidence levels to object-specific predictions. This contrasts to current best-practices where the overall confidence level for predictions on unseen objects is estimated based on previous performance, assuming exchangeability. Here we report a Spark-based distributed implementation of conformal prediction, which introduces valid confidence estimation in predictive modeling for Big Data analytics. Experimental results on two large-scale datasets show the validity and the scalabilty of the method, which is freely available as open source. © 2015 ACM. Source

Ahlberg E.,Astrazeneca | Carlsson L.,Astrazeneca | Boyer S.,Astrazeneca | Boyer S.,Swedish Toxicology science Research Center
Journal of Chemical Information and Modeling

Structural alerts have been one of the backbones of computational toxicology and have applications in many areas including cosmetic, environmental, and pharmaceutical toxicology. The development of structural alerts has always involved a manual analysis of existing data related to a relevant end point followed by the determination of substructures that appear to be related to a specific outcome. The substructures are then analyzed for their utility in posterior validation studies, which at times have stretched over years or even decades. With higher throughput methods now being employed in many areas of toxicology, data sets are growing at an unprecedented rate. This growth has made manual analysis of data sets impractical in many cases. This report outlines a fully automatic method that highlights significant substructures for toxicologically important data sets. The method identifies important substructures by computationally breaking chemical structures into fragments and analyzing those fragments for their contribution to the given activity by the calculation of a p-value and a substructure accuracy. The method is intended to aid the expert in locating and analyzing alerts by automatic retrieval of alerts or by enhancing existing alerts. The method has been applied to a data set of AMES mutagenicity results and compared to the substructures generated by manual curation of this same data set as well as another computationally based substructure identification method. The results show that this method can retrieve significant substructures quickly, that the substructures are comparable and in some cases superior to those derived from manual curation, that the substructures found covers all previously known substructures, and that they can be used to make reasonably accurate predictions of AMES activity. © 2014 American Chemical Society. Source

Discover hidden collaborations